An official website of the United States government
In this paper, we propose a machine learning-based multi-stream framework to recognize American Sign Language (ASL) manual signs and nonmanual gestures (face and head movements) in real time from RGB-D videos. Our approach is based on 3D Convolutional Neural Networks (3D CNNs) by fusing the multi-modal features including hand gestures, facial expressions, and body poses from multiple channels (RGB, Depth, Motion, and Skeleton joints). To learn the overall temporal dynamics in a video, a proxy video is generated by selecting a subset of frames for each video which are then used to train the proposed 3D CNN model. We collected a new ASL dataset, ASL-100-RGBD, which contains 42 RGB-D videos captured by a Microsoft Kinect V2 camera. Each video consists of 100 ASL manual signs, along with RGB channel, Depth maps, Skeleton joints, Face features, and HD face. The dataset is fully annotated for each semantic region (i.e. the time duration of each sign that the human signer performs). Our proposed method achieves 92.88% accuracy for recognizing 100 ASL sign glosses in our newly collected ASL-100-RGBD dataset. The effectiveness of our framework for recognizing hand gestures from RGB-D videos is further demonstrated on a large-scale dataset, ChaLearn IsoGD, achieving the state-of-the-art results.
more »
« less
Controllable Radiance Fields for Dynamic Face Synthesis
Recent work on 3D-aware image synthesis has achieved compelling results using advances in neural rendering. However, 3D-aware synthesis of face dynamics hasn't received much attention. Here, we study how to explicitly control generative model synthesis of face dynamics exhibiting non-rigid motion (e.g., facial expression change), while simultaneously ensuring 3D-awareness. For this we propose a Controllable Radiance Field (CoRF): 1) Motion control is achieved by embedding motion features within the layered latent motion space of a style-based generator; 2) To ensure consistency of background, motion features and subject-specific attributes such as lighting, texture, shapes, albedo, and identity, a face parsing net, a head regressor and an identity encoder are incorporated. On head image/video data we show that CoRFs are 3D-aware while enabling editing of identity, viewing directions, and motion.
more »
« less
- PAR ID:
- 10387045
- Date Published:
- Journal Name:
- 3DV
- ISSN:
- 0219-6921
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
An object’s interior material properties, while invisible to the human eye, determine motion observed on its surface. We propose an approach that esti- mates heterogeneous material properties of an object directly from a monoc- ular video of its surface vibrations. Specifically, we estimate Young’s modulus and density throughout a 3D object with known geometry. Knowledge of how these values change across the object is useful for characterizing defects and simulating how the object will interact with different environments. Traditional non-destructive testing approaches, which generally estimate homogenized material properties or the presence of defects, are expensive and use specialized instruments. We propose an approach that leverages monocular video to (1) measure an object’s sub-pixel motion and decompose this motion into image-space modes, and (2) directly infer spatially-varying Young’s modulus and density values from the observed image-space modes. On both simulated and real videos, we demonstrate that our approach is able to image material properties simply by analyzing surface motion. In particular, our method allows us to identify unseen defects on a 2D drum head from real, high-speed video.more » « less
-
Recovering 3D face models from in-the-wild face images has numerous potential applications. However, properly modeling complex lighting effects in reality, including specular lighting, shadows, and occlusions, from a single in-the-wild face image is still considered as a widely open research challenge. In this paper, we propose a convolutional neural network based framework to regress the face model from a single image in the wild. The outputted face model includes dense 3D shape, head pose, expression, diffuse albedo, specular albedo, and the corresponding lighting conditions. Our approach uses novel hybrid loss functions to disentangle face shape identities, expressions, poses, albedos, and lighting. Besides a carefully designed ablation study, we also conduct direct comparison experiments to show that our method can outperform state-of-art methods both quantitatively and qualitatively.more » « less
-
Abstract The development of high-resolution microscopes has made it possible to investigate cellular processes in 3D and over time. However, observing fast cellular dynamics remains challenging because of photobleaching and phototoxicity. Here we report the implementation of two content-aware frame interpolation (CAFI) deep learning networks, Zooming SlowMo and Depth-Aware Video Frame Interpolation, that are highly suited for accurately predicting images in between image pairs, therefore improving the temporal resolution of image series post-acquisition. We show that CAFI is capable of understanding the motion context of biological structures and can perform better than standard interpolation methods. We benchmark CAFI’s performance on 12 different datasets, obtained from four different microscopy modalities, and demonstrate its capabilities for single-particle tracking and nuclear segmentation. CAFI potentially allows for reduced light exposure and phototoxicity on the sample for improved long-term live-cell imaging. The models and the training and testing data are available via the ZeroCostDL4Mic platform.more » « less
-
We introduce a method for novel view synthesis given only a single wide-baseline stereo image pair. In this challenging regime, 3D scene points are regularly observed only once, requiring prior-based reconstruction of scene geometry and appearance. We find that existing approaches to novel view synthesis from sparse observations fail due to recovering incorrect 3D geometry and due to the high cost of differentiable rendering that precludes their scaling to large-scale training. We take a step towards resolving these shortcomings by formulating a multi-view transformer encoder, proposing an efficient, image-space epipolar line sampling scheme to assemble image features for a target ray, and a lightweight cross-attention-based renderer. Our contributions enable training of our method on a large-scale real-world dataset of indoor and outdoor scenes. We demonstrate that our method learns powerful multi-view geometry priors while reducing both rendering time and memory footprint. We conduct extensive comparisons on held-out test scenes across two real-world datasets, significantly outperforming prior work on novel view synthesis from sparse image observations and achieving multi-view-consistent novel view synthesis.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
